© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 44258
    Prev
    Next
    INDEX
    Explanations

    dimension, cosine, metric, similarity, loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ты
    0.91
    Desktop
    0.89
     سای
    0.87
    ımlar
    0.87
    本项目
    0.86
    钅
    0.86
    ithi
    0.85
     왕
    0.85
    IS
    0.84
     同
    0.83
    POSITIVE LOGITS
    ierungs
    0.88
    вання
    0.86
     शकतात
    0.84
     chemot
    0.83
     shampoo
    0.82
    άνει
    0.80
    scrollTop
    0.79
     freezer
    0.79
     Tener
    0.78
    ηση
    0.77
    Activations Density 0.087%

    No Known Activations